On the modeling and optimization of short-term performance for real-time wireless networks

This paper studies wireless networks consisting of multiple real-time flows that impose hard delay bounds for all packets. In contrast to most current studies that focus on the long-term average rate of timely deliveries, we aim to model and optimize the short-term performance of each real-time flow, which is vital for most safety-critical applications. We propose to define the instantaneous performance of a flow by a moving average within a short window in the past. Each flow incurs some penalty if its moving average is below some specified requirement, and we aim to minimize the overall penalty of the system. We approximate the system by Brownian motions, and formulate an optimization problem for minimizing the overall penalty. While the optimization problem is not convex, we establish a low-complexity algorithm for optimally solving it by leveraging inherent structures of real-time wireless networks. We also propose a simple online packet scheduling policy and prove that it achieves the minimum overall penalty. Simulation results show that Brownian approximations are accurate in capturing short-term performance, and our policies achieve much better performance than other policies. Moreover, they also demonstrate that policies with optimal long-term average delivery rates can actually have poor short-term performance.